Anthropic said its Mythos 5 model almost never stopped a cyberattack once it began. Even when the agent was told it was harming real people? Crickets.

Log in or sign up to comment.

No comments yet.

← Back to stories

Create FREE account

or login to continue

Signup with GoogleSignup with GitHubSignup with BlueskySignup with Blacksky
Sign up with email

Already have an account? Log in